Evaluating the utility of mid-infrared spectral subspaces for predicting soil properties


Andrew M. Sila, Keith D. Shepherd, Ganesh P. Pokhariyal

Ab s t r a c t
We propose four methods for finding local subspaces in large spectral libraries. The proposed four methods include
(a) cosine angle spectral matching; (b) hit quality index spectral matching; (c) self-organizing maps and
(d) archetypal analysis methods. Then evaluate prediction accuracies for global and subspaces calibration
models. These methods were tested on a mid-infrared spectral library containing 1907 soil samples collected
from 19 different countries under the Africa Soil Information Service project. Calibration models for pH,
Mehlich-3 Ca, Mehlich-3 Al, total carbon and clay soil properties were developed for the whole library and for
the subspace. Root mean square error of prediction was used to evaluate predictive performance of subspace
and global models. The root mean square error of predictionwas computed using a one-third-holdout validation
set. Effect of pretreating spectra with different methods was tested for 1st and 2nd derivative Savitzky–Golay
algorithm, multiplicative scatter correction, standard normal variate and standard normal variate followed by
detrending methods. In summary, the results show that global models outperformed the subspace models.
We, therefore, conclude that global models are more accurate than the local models except in few cases. For instance,
sand and clay root mean square error values fromlocalmodels fromarchetypal analysismethodwere 50%
poorer than the globalmodels except for subspace models obtained usingmultiplicative scatter corrected spectra
with which were 12% better. However, the subspace approach provides novel methods for discovering data pattern
that may exist in large spectral libraries.

End Year: 
1-s2.0-S0169743916300351-main.pdf1.84 MB

Message From the Director

Workshops and Seminars

Community Outreach

Contact Us

School of Mathematics, CBPS College.

P. O. Box 30197 - 00100
Tel: 254-02-4445751.

Mobile no :0780-834766.
Email: maths@uonbi.ac.ke.




UoN Website | UoN Repository | ICTC Website

Copyright © 2019. ICT WebTeam, University of Nairobi